CVPR 2016 accepted papers on Vision-language and multimodal
33 of the 643 papers accepted at CVPR 2016 (5.1%) are on Vision-language and multimodal. They fall into 4 topics.
See CVPR 2016 in the interactive map
Submitting to CVPR? Checklist →
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Human and embodied modeling · 15 papers
- Image Captioning With Semantic Attention (1,739 citations)
- Robust Scene Text Recognition With Automatic Rectification (710 citations)
- Jointly Modeling Embedding and Translation to Bridge Video and Language (598 citations)
- Natural Language Object Retrieval (588 citations)
- Sketch Me That Shoe (443 citations)
- TGIF: A New Dataset and Benchmark on Animated GIF Description (210 citations)
- Large-Scale Location Recognition and the Geometric Burstiness Problem (156 citations)
- Visual Word2Vec (vis-w2v): Learning Visually Grounded Word Embeddings Using Abstract Scenes (86 citations)
- Some Like It Hot - Visual Guidance for Preference Prediction (74 citations)
- We Are Humor Beings: Understanding and Predicting Visual Humor (49 citations)
- Event-Specific Image Importance (40 citations)
- Predicting Motivations of Actions by Leveraging Text (40 citations)
and 3 more in the interactive map.
Visual question answering · 8 papers
- Stacked Attention Networks for Image Question Answering (2,094 citations)
- Neural Module Networks (994 citations)
- Visual7W: Grounded Question Answering in Images (804 citations)
- Where to Look: Focus Regions for Visual Question Answering (538 citations)
- What Value Do Explicit High Level Concepts Have in Vision to Language Problems? (482 citations)
- Ask Me Anything: Free-Form Visual Question Answering Based on Knowledge From External Sources (369 citations)
- Yin and Yang: Balancing and Answering Binary Visual Questions (320 citations)
- Answer-Type Prediction for Visual Question Answering (132 citations)
Cross-modal learning · 7 papers
- Cross Modal Distillation for Supervision Transfer (555 citations)
- Learning Aligned Cross-Modal Representations From Weakly Aligned Data (197 citations)
- Discriminative Multi-Modal Feature Fusion for RGBD Indoor Scene Recognition (115 citations)
- Temporal Multimodal Learning in Audiovisual Speech Recognition (113 citations)
- Collaborative Quantization for Cross-Modal Similarity Search (63 citations)
- Aggregating Image and Text Quantized Correlated Components (25 citations)
- MDL-CW: A Multimodal Deep Learning Framework With Cross Weights
CLIP and zero-shot · 3 papers
- Learning Deep Representations of Fine-Grained Visual Descriptions (799 citations)
- Less Is More: Zero-Shot Learning From Online Textual Documents With Noise Suppression (187 citations)
- Fast Zero-Shot Image Tagging (75 citations)
